URSA：基于星座的无序点云神经网络
URSA: A Neural Network for Unordered Point Clouds Using Constellations
摘要：
本文描述了一个名为Ursa的神经网络层，它使用一组点从点云数据中学习分类信息。与其他机器学习分类问题的任务是对单个高维观测进行分类不同，在点云分类问题中，目标是对一组d维观测进行分类。由于点云是一个集合，因此点云分类问题中的点集合没有顺序。因此，对点云输入进行分类的挑战在于构建一个分类器，该分类器对观测的排序是不可知的，但保留了集合中每个点的d维信息。本研究提出了Ursa，一种新的层类型的人工神经网络，实现这两个属性。与此任务的新方法类似，该架构直接在d维点上工作，而不是首先将点转换为d维体积。Ursa层之后是一系列密集层，用于从点云中分类2D和3D对象。在ModelNet40和MNIST数据上的实验表明，分类结果与当前方法相当，同时将训练参数减少了50%以上。
英文摘要：
This paper describes a neural network layer, named Ursa, that uses a constellation of points to learn classification information from point cloud data. Unlike other machine learning classification problems where the task is to classify an individual high-dimensional observation, in a point-cloud classification problem the goal is to classify a set of d-dimensional observations. Because a point cloud is a set, there is no ordering to the collection of points in a point-cloud classification problem. Thus, the challenge of classifying point clouds inputs is in building a classifier which is agnostic to the ordering of the observations, yet preserves the d-dimensional information of each point in the set. This research presents Ursa, a new layer type for an artificial neural network which achieves these two properties. Similar to new methods for this task, this architecture works directly on d-dimensional points rather than first converting the points to a d-dimensional volume. The Ursa layer is followed by a series of dense layers to classify 2D and 3D objects from point clouds. Experiments on ModelNet40 and MNIST data show classification results comparable with current methods, while reducing the training parameters by over 50 percent.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
